arXiv AI
Engineering Efficient Self-Play Chess: Search, Replay, and Throughput Under Limited Compute
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 10
The Surprising Effectiveness of Approximate Value Iteration in Self-Play
arXiv:2609.09094v1 Announce Type: new Abstract: Combining search with function approximation has driven major advances in game-playing programs, making self-play algorithms more competitive than ever...
arXiv AI
Sep 15
Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed Bandits
arXiv:2605.29268v3 Announce Type: replace-cross Abstract: LLM-guided evolutionary search (Evolve systems) has reached state-of-the-art results on mathematical and combinatorial tasks, yet most existi...
arXiv AI
1d ago
KV-streams for Efficient Compaction in Agentic Reinforcement Learning
arXiv:2609.35750v2 Announce Type: replace-cross Abstract: Scaling the horizon of agentic LLMs is bottlenecked by the need to fit ever longer context traces in GPU memory. Context compaction has been...
arXiv Machine Learning
Aug 31
Beyond Search-Imitation: Prior-Directed Exploration for Searchless Chess
arXiv:2608.27757v1 Announce Type: new Abstract: Searchless chess networks reach human master strength from a single forward pass by imitating a stronger teacher: the strongest, Leela Chess Zero's (Lc...
arXiv Computation and Language
Sep 15
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
arXiv:2609.14858v1 Announce Type: new Abstract: Recursive self-improvement is becoming increasingly vital for autonomous AI agents, where progress hinges on discovering high-value solutions across co...
arXiv AI
Jun 18
Spotlight: Synergizing Seed Exploration and Spot GPUs for DiT RL Post-Training
arXiv:2606. 19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs.